Triple
T538544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Table Bay |
E12378
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Bloubergstrand |
E55910
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Bloubergstrand | Statement: [Table Bay, near, Bloubergstrand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bloubergstrand Context triple: [Table Bay, near, Bloubergstrand]
-
A.
Hermanus
Hermanus is a coastal town in South Africa renowned for its land-based whale watching and scenic seaside landscapes.
-
B.
Mossel Bay
Mossel Bay is a coastal town and popular tourist destination on South Africa’s Garden Route, known for its beaches, mild climate, and maritime history.
-
C.
Knysna
Knysna is a picturesque coastal town in South Africa known for its lagoon, indigenous forests, and role as a major tourist destination along the Garden Route.
-
D.
Colva Beach
Colva Beach is a well-known tourist beach in South Goa, India, famed for its long stretch of white sand, palm-lined shore, and vibrant seaside atmosphere.
-
E.
Saldanha Bay
chosen
Saldanha Bay is a natural deep-water harbor and coastal town on South Africa’s west coast, known for its fishing industry, port facilities, and maritime activities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a4933208e88190891f5debab1b776d |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a496dd31c88190b3114805aa31931c |
completed | March 1, 2026, 7:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4c66fa348819081e004fb4350f4ea |
completed | March 1, 2026, 11:06 p.m. |
Created at: March 1, 2026, 7:32 p.m.